Improving active learning methods using spatial information

Author

Pasolli, Edoardo ; Melgani, Farid ; Tuia, Devis ; Pacifici, Fabio ; Emery, William J.

Author_Institution

Dept. of Inf. Eng. & Comput. Sci., Univ. of Trento, Trento, Italy

fYear

2011

fDate

24-29 July 2011

Firstpage

3923

Lastpage

3926

Abstract

Active learning process represents an interesting solution to the problem of training sample collection for the classification of remote sensing images. In this work, we propose a criterion based on the spatial information that can be used in combination with a spectral criterion in order to improve the selection of training samples. Experimental results obtained on a very high resolution image show the effectiveness of regularization in spatial domain and open challenging perspectives for terrain campaigns planning.

Keywords

geophysical image processing; image classification; image resolution; learning (artificial intelligence); remote sensing; active learning; remote sensing image classification; spatial information; spectral criterion; terrain campaign planning; very high resolution image; Accuracy; Learning systems; Machine learning; Remote sensing; Spatial resolution; Support vector machines; Training; Active learning; spatial information; support vector machines (SVMs); very-high-resolution (VHR) images;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International

Conference_Location

Vancouver, BC

ISSN

2153-6996

Print_ISBN

978-1-4577-1003-2

Type

conf

DOI

10.1109/IGARSS.2011.6050089

Filename

6050089